Knowledge / Physical AI Signals

Physical AI Signals

A dated stream of notable developments in embodied AI, robot foundation models, humanoids and robot learning.

September 17, 2026

Isaac Lab updated

NVIDIA describes Isaac Lab as an open-source GPU-accelerated framework for robot learning, built on Isaac Sim and supporting reinforcement and imitation learning.

NVIDIA source →
September 15, 2026

Agility unveils Digit 5

Agility announced the next-generation Digit 5, describing it as engineered for cooperatively safe work at scale and building on more than 65,000 hours of operation and commercial deployments.

Agility source →
September 10, 2026

Skild AI introduces S1

NVIDIA reported that Skild AI's S1 robot foundation model can learn previously unseen long-horizon tasks from a single video demonstration through in-context learning.

NVIDIA source →
July 30, 2026

Gemini Robotics 2

Google DeepMind introduced Gemini Robotics 2, alongside Gemini Robotics ER 2 and On-Device 2, describing whole-body control, dexterity, multi-robot collaboration and adaptation across embodiments.

Google DeepMind source →

Primary source

Read the primary source →

Editorial guide · Reviewed September 2026 · Editorial policy